config.json

{
  "architectures": [
    "ModernBertForSequenceClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 2,
  "classifier_activation": "gelu",
  "classifier_bias": false,
  "classifier_dropout": 0.0,
  "classifier_pooling": "mean",
  "cls_token_id": 1,
  "decoder_bias": true,
  "deterministic_flash_attn": false,
  "dtype": "float32",
  "embedding_dropout": 0.0,
  "eos_token_id": 1,
  "global_attn_every_n_layers": 3,
  "gradient_checkpointing": false,
  "hidden_activation": "gelu",
  "hidden_size": 384,
  "id2label": {
    "0": "ko",
    "1": "no",
    "2": "da",
    "3": "sv",
    "4": "fi",
    "5": "nl",
    "6": "en",
    "7": "fr",
    "8": "de",
    "9": "es",
    "10": "pt",
    "11": "it",
    "12": "ja",
    "13": "UNKNOWN"
  },
  "initializer_cutoff_factor": 2.0,
  "initializer_range": 0.02,
  "intermediate_size": 1152,
  "label2id": {
    "UNKNOWN": 13,
    "da": 2,
    "de": 8,
    "en": 6,
    "es": 9,
    "fi": 4,
    "fr": 7,
    "it": 11,
    "ja": 12,
    "ko": 0,
    "nl": 5,
    "no": 1,
    "pt": 10,
    "sv": 3
  },
  "layer_norm_eps": 1e-05,
  "layer_types": [
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "sliding_attention",
    "full_attention"
  ],
  "local_attention": 128,
  "mask_token_id": 4,
  "max_position_embeddings": 8192,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "model_type": "modernbert",
  "norm_bias": false,
  "norm_eps": 1e-05,
  "num_attention_heads": 6,
  "num_hidden_layers": 22,
  "pad_token_id": 0,
  "position_embedding_type": "sans_pos",
  "problem_type": "single_label_classification",
  "rope_parameters": {
    "full_attention": {
      "rope_theta": 160000,
      "rope_type": "default"
    },
    "sliding_attention": {
      "rope_theta": 160000,
      "rope_type": "default"
    }
  },
  "sep_token_id": 1,
  "sparse_pred_ignore_index": -100,
  "sparse_prediction": false,
  "tie_word_embeddings": true,
  "transformers_version": "5.3.0",
  "use_cache": false,
  "vocab_size": 256000
}